Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety bar is partly covered. The description adds real value beyond them: it warns that raw connection IDs are rejected and must be replaced with workspace-scoped targetKey values, and it clarifies that no work is started or saved by the preview. It stops short of describing revision-conflict behavior, which matters for a revision-guarded call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core verb and resource, each contributing something. Minor redundancy: "The preview is read-only" restates readOnlyHint, though it earns its place by adding the consequence that work is not started.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. However, for a nine-parameter tool with nested object inputs and two revision guards, the description covers only one parameter and one behavioral nuance, leaving the agent to guess how action, request/patch, and expected revisions interact before it can call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across nine parameters including two deeply nested objects, so the description carries the full burden. It clarifies only targetChannelKeys (exact workspace-scoped targetKey values, raw connection IDs rejected) and leaves action's six enum values, expectedPostRevision vs expectedRequestRevision, request vs patch, jobId, and idempotencyKey entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ("Previews a revision-guarded Post media request change") and adds a scope qualifier (revision-guarded) that tells the agent this is a dry-run against an expected revision. It is clearly distinct from sibling preview tools by naming the resource, though it never explicitly contrasts with get_post_media_request, the sibling that reads current state.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies the preview-then-apply workflow by stating that "saving or starting image/video work requires application of a later proposal," which tells the agent this call is the check step, not the write step. It gives no explicit when-to-use vs when-not, no named alternative for retrieving current state, and no guidance on which of the six action values warrants a preview.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.